Preprint · 2021 · Open access
Enabling Inference Privacy with Adaptive Noise Injection
arXiv (Cornell University) · Published 6 April 2021 · DOI 10.48550/arxiv.2104.02261
In brief
“Enabling Inference Privacy with Adaptive Noise Injection” is a 2021 preprint by Sanjay Kariyappa and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 7 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 7
- Most cited in
- 2024 (2)
- References
- 24
- Authors
- 3
Abstract
User-facing software services are becoming increasingly reliant on remote servers to host Deep Neural Network (DNN) models, which perform inference tasks for the clients. Such services require the client to send input data to the service provider, who processes it using a DNN and returns the output predictions to the client. Due to the rich nature of the inputs such as images and speech, the input often contains more information than what is necessary to perform the primary inference task. Consequently, in addition to the primary inference task, a malicious service provider could infer secondary (sensitive) attributes from the input, compromising the client's privacy. The goal of our work is to improve inference privacy by injecting noise to the input to hide the irrelevant features that are not conducive to the primary classification task. To this end, we propose Adaptive Noise Injection (ANI), which uses a light-weight DNN on the client-side to inject noise to each input, before transmitting it to the service provider to perform inference. Our key insight is that by customizing the noise to each input, we can achieve state-of-the-art trade-off between utility and privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy), significantly outperforming existing noise injection schemes. Our method does not require prior knowledge of the sensitive attributes and incurs minimal computational overheads.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Kariyappa, S., Dia, O., & Qureshi, M. K. (2021). Enabling Inference Privacy with Adaptive Noise Injection. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2104.02261
MLA 9
Kariyappa, Sanjay, et al. “Enabling Inference Privacy with Adaptive Noise Injection.” arXiv (Cornell University), 2021. https://doi.org/10.48550/arxiv.2104.02261.
Chicago
Kariyappa, Sanjay, Ousmane Dia, and Moinuddin K. Qureshi. 2021. “Enabling Inference Privacy with Adaptive Noise Injection.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2104.02261.
Harvard
Kariyappa, S., Dia, O. and Qureshi, M. K. (2021) ‘Enabling Inference Privacy with Adaptive Noise Injection’, arXiv (Cornell University). doi:10.48550/arxiv.2104.02261.
IEEE
S. Kariyappa, O. Dia, and M. K. Qureshi, “Enabling Inference Privacy with Adaptive Noise Injection,” arXiv (Cornell University), 2021, doi: 10.48550/arxiv.2104.02261.
BibTeX
@misc{kariyappa2021enabling,
title = {{Enabling Inference Privacy with Adaptive Noise Injection}},
author = {Kariyappa, Sanjay and Dia, Ousmane and Qureshi, Moinuddin K.},
howpublished = {arXiv (Cornell University)},
year = {2021},
doi = {10.48550/arxiv.2104.02261},
url = {https://doi.org/10.48550/arxiv.2104.02261}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2022 | 1 | |
| 2023 | 1 | |
| 2024 | 2 | |
| 2025 | 1 | |
| 2026 | 2 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- inference privacy
- adaptive noise injection
- privacy-utility trade-off
- sensitive attribute inference
- privacy-preserving machine learning
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Kariyappa, S., Dia, O., & Qureshi, M. K. (2021). Enabling Inference Privacy with Adaptive Noise Injection. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2104.02261
How many times has this paper been cited?
7 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Sanjay Kariyappa, Ousmane Dia, Moinuddin K. Qureshi.
What is the DOI of this paper?
10.48550/arxiv.2104.02261, permanently at https://doi.org/10.48550/arxiv.2104.02261. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.